Allow vectorization of intrinsics such as powi,cttz and ctlz in Loop and SLP Vectorizer.

This patch adds support to vectorize intrinsics such as powi, cttz and ctlz in Vectorizer. These intrinsics are different from other
intrinsics as second argument to these function must be same in order to vectorize them and it should be represented as a scalar.
Review: http://reviews.llvm.org/D3851#inline-32769 and http://reviews.llvm.org/D3937#inline-32857

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@209873 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/include/llvm/Transforms/Utils/VectorUtils.h b/include/llvm/Transforms/Utils/VectorUtils.h
index e1d6c562923b03db94b99877ca6aaade62938e82..44a7149eee980df0b7abd4c571af6b53fee7d859 100644 (file)
--- a/include/llvm/Transforms/Utils/VectorUtils.h
+++ b/include/llvm/Transforms/Utils/VectorUtils.h
@@ -48,12 +48,27 @@ static inline bool isTriviallyVectorizable(Intrinsic::ID ID) {
   case Intrinsic::pow:
   case Intrinsic::fma:
   case Intrinsic::fmuladd:
+  case Intrinsic::ctlz:
+  case Intrinsic::cttz:
+  case Intrinsic::powi:
     return true;
   default:
     return false;
   }
 }
 
+static bool hasVectorInstrinsicScalarOpd(Intrinsic::ID ID,
+                                         unsigned ScalarOpdIdx) {
+  switch (ID) {
+    case Intrinsic::ctlz:
+    case Intrinsic::cttz:
+    case Intrinsic::powi:
+      return (ScalarOpdIdx == 1);
+    default:
+      return false;
+  }
+}
+
 static Intrinsic::ID checkUnaryFloatSignature(const CallInst &I,
                                               Intrinsic::ID ValidIntrinsicID) {
   if (I.getNumArgOperands() != 1 ||

diff --git a/lib/Transforms/Vectorize/LoopVectorize.cpp b/lib/Transforms/Vectorize/LoopVectorize.cpp
index ba2b7eea363ffc5cb50619df145d2fdbb86a2a3a..15d4c1c79d2b502308171a736a04577fe2a59067 100644 (file)
--- a/lib/Transforms/Vectorize/LoopVectorize.cpp
+++ b/lib/Transforms/Vectorize/LoopVectorize.cpp
@@ -3123,9 +3123,14 @@ void InnerLoopVectorizer::vectorizeBlockInLoop(BasicBlock *BB, PhiVector *PV) {
         scalarizeInstruction(it);
         break;
       default:
+        bool HasScalarOpd = hasVectorInstrinsicScalarOpd(ID, 1);
         for (unsigned Part = 0; Part < UF; ++Part) {
           SmallVector<Value *, 4> Args;
           for (unsigned i = 0, ie = CI->getNumArgOperands(); i != ie; ++i) {
+            if (HasScalarOpd && i == 1) {
+              Args.push_back(CI->getArgOperand(i));
+              continue;
+            }
             VectorParts &Arg = getVectorValue(CI->getArgOperand(i));
             Args.push_back(Arg[Part]);
           }
@@ -3474,6 +3479,16 @@ bool LoopVectorizationLegality::canVectorizeInstrs() {
         return false;
       }
 
+      // Intrinsics such as powi,cttz and ctlz are legal to vectorize if the
+      // second argument is the same (i.e. loop invariant)
+      if (CI &&
+          hasVectorInstrinsicScalarOpd(getIntrinsicIDForCall(CI, TLI), 1)) {
+        if (!SE->isLoopInvariant(SE->getSCEV(CI->getOperand(1)), TheLoop)) {
+          DEBUG(dbgs() << "LV: Found unvectorizable intrinsic " << *CI << "\n");
+          return false;
+        }
+      }
+
       // Check that the instruction return type is vectorizable.
       // Also, we can't vectorize extractelement instructions.
       if ((!VectorType::isValidElementType(it->getType()) &&

diff --git a/lib/Transforms/Vectorize/SLPVectorizer.cpp b/lib/Transforms/Vectorize/SLPVectorizer.cpp
index e13ba956c398eb9f14490ca256ee90850cfd9a10..ce0a009e1cb147cda9bd8072ebeaa9c0bb8dd614 100644 (file)
--- a/lib/Transforms/Vectorize/SLPVectorizer.cpp
+++ b/lib/Transforms/Vectorize/SLPVectorizer.cpp
@@ -961,9 +961,10 @@ void BoUpSLP::buildTree_rec(ArrayRef<Value *> VL, unsigned Depth) {
         DEBUG(dbgs() << "SLP: Non-vectorizable call.\n");
         return;
       }
-
       Function *Int = CI->getCalledFunction();
-
+      Value *A1I = nullptr;
+      if (hasVectorInstrinsicScalarOpd(ID, 1))
+        A1I = CI->getArgOperand(1);
       for (unsigned i = 1, e = VL.size(); i != e; ++i) {
         CallInst *CI2 = dyn_cast<CallInst>(VL[i]);
         if (!CI2 || CI2->getCalledFunction() != Int ||
@@ -973,6 +974,18 @@ void BoUpSLP::buildTree_rec(ArrayRef<Value *> VL, unsigned Depth) {
                        << "\n");
           return;
         }
+        // ctlz,cttz and powi are special intrinsics whose second argument
+        // should be same in order for them to be vectorized.
+        if (hasVectorInstrinsicScalarOpd(ID, 1)) {
+          Value *A1J = CI2->getArgOperand(1);
+          if (A1I != A1J) {
+            newTreeEntry(VL, false);
+            DEBUG(dbgs() << "SLP: mismatched arguments in call:" << *CI
+                         << " argument "<< A1I<<"!=" << A1J
+                         << "\n");
+            return;
+          }
+        }
       }
 
       newTreeEntry(VL, true);
@@ -1652,9 +1665,21 @@ Value *BoUpSLP::vectorizeTree(TreeEntry *E) {
     case Instruction::Call: {
       CallInst *CI = cast<CallInst>(VL0);
       setInsertPointAfterBundle(E->Scalars);
+      Function *FI;
+      Intrinsic::ID IID  = Intrinsic::not_intrinsic;
+      if (CI && (FI = CI->getCalledFunction())) {
+        IID = (Intrinsic::ID) FI->getIntrinsicID();
+      }
       std::vector<Value *> OpVecs;
       for (int j = 0, e = CI->getNumArgOperands(); j < e; ++j) {
         ValueList OpVL;
+        // ctlz,cttz and powi are special intrinsics whose second argument is
+        // a scalar. This argument should not be vectorized.
+        if (hasVectorInstrinsicScalarOpd(IID, 1) && j == 1) {
+          CallInst *CEI = cast<CallInst>(E->Scalars[0]);
+          OpVecs.push_back(CEI->getArgOperand(j));
+          continue;
+        }
         for (int i = 0, e = E->Scalars.size(); i < e; ++i) {
           CallInst *CEI = cast<CallInst>(E->Scalars[i]);
           OpVL.push_back(CEI->getArgOperand(j));

diff --git a/test/Transforms/LoopVectorize/intrinsic.ll b/test/Transforms/LoopVectorize/intrinsic.ll
index c3d570c03a77fbf9ebcf97fe42f91b547243f846..7dfaf03b0f2d7988b52134720098db5e32a9a5ac 100644 (file)
--- a/test/Transforms/LoopVectorize/intrinsic.ll
+++ b/test/Transforms/LoopVectorize/intrinsic.ll
@@ -1090,3 +1090,105 @@ for.end:                                          ; preds = %for.body
   ret void
 }
 
+declare double @llvm.powi.f64(double %Val, i32 %power) nounwind readnone
+
+;CHECK-LABEL: @powi_f64(
+;CHECK: llvm.powi.v4f64
+;CHECK: ret void
+define void @powi_f64(i32 %n, double* noalias %y, double* noalias %x, i32 %P) nounwind uwtable {
+entry:
+  %cmp9 = icmp sgt i32 %n, 0
+  br i1 %cmp9, label %for.body, label %for.end
+
+for.body:                                         ; preds = %entry, %for.body
+  %indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
+  %arrayidx = getelementptr inbounds double* %y, i64 %indvars.iv
+  %0 = load double* %arrayidx, align 8
+  %call = tail call double @llvm.powi.f64(double %0, i32  %P) nounwind readnone
+  %arrayidx4 = getelementptr inbounds double* %x, i64 %indvars.iv
+  store double %call, double* %arrayidx4, align 8
+  %indvars.iv.next = add i64 %indvars.iv, 1
+  %lftr.wideiv = trunc i64 %indvars.iv.next to i32
+  %exitcond = icmp eq i32 %lftr.wideiv, %n
+  br i1 %exitcond, label %for.end, label %for.body
+
+for.end:                                          ; preds = %for.body, %entry
+  ret void
+}
+
+;CHECK-LABEL: @powi_f64_neg(
+;CHECK-NOT: llvm.powi.v4f64
+;CHECK: ret void
+define void @powi_f64_neg(i32 %n, double* noalias %y, double* noalias %x) nounwind uwtable {
+entry:
+  %cmp9 = icmp sgt i32 %n, 0
+  br i1 %cmp9, label %for.body, label %for.end
+
+for.body:                                         ; preds = %entry, %for.body
+  %indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
+  %arrayidx = getelementptr inbounds double* %y, i64 %indvars.iv
+  %0 = load double* %arrayidx, align 8
+  %1 = trunc i64 %indvars.iv to i32
+  %call = tail call double @llvm.powi.f64(double %0, i32  %1) nounwind readnone
+  %arrayidx4 = getelementptr inbounds double* %x, i64 %indvars.iv
+  store double %call, double* %arrayidx4, align 8
+  %indvars.iv.next = add i64 %indvars.iv, 1
+  %lftr.wideiv = trunc i64 %indvars.iv.next to i32
+  %exitcond = icmp eq i32 %lftr.wideiv, %n
+  br i1 %exitcond, label %for.end, label %for.body
+
+for.end:                                          ; preds = %for.body, %entry
+  ret void
+}
+
+declare i64  @llvm.cttz.i64 (i64, i1) nounwind readnone
+
+;CHECK-LABEL: @cttz_f64(
+;CHECK: llvm.cttz.v4i64
+;CHECK: ret void
+define void @cttz_f64(i32 %n, i64* noalias %y, i64* noalias %x) nounwind uwtable {
+entry:
+  %cmp9 = icmp sgt i32 %n, 0
+  br i1 %cmp9, label %for.body, label %for.end
+
+for.body:                                         ; preds = %entry, %for.body
+  %indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
+  %arrayidx = getelementptr inbounds i64* %y, i64 %indvars.iv
+  %0 = load i64* %arrayidx, align 8
+  %call = tail call i64 @llvm.cttz.i64(i64 %0, i1 true) nounwind readnone
+  %arrayidx4 = getelementptr inbounds i64* %x, i64 %indvars.iv
+  store i64 %call, i64* %arrayidx4, align 8
+  %indvars.iv.next = add i64 %indvars.iv, 1
+  %lftr.wideiv = trunc i64 %indvars.iv.next to i32
+  %exitcond = icmp eq i32 %lftr.wideiv, %n
+  br i1 %exitcond, label %for.end, label %for.body
+
+for.end:                                          ; preds = %for.body, %entry
+  ret void
+}
+
+declare i64  @llvm.ctlz.i64 (i64, i1) nounwind readnone
+
+;CHECK-LABEL: @ctlz_f64(
+;CHECK: llvm.ctlz.v4i64
+;CHECK: ret void
+define void @ctlz_f64(i32 %n, i64* noalias %y, i64* noalias %x) nounwind uwtable {
+entry:
+  %cmp9 = icmp sgt i32 %n, 0
+  br i1 %cmp9, label %for.body, label %for.end
+
+for.body:                                         ; preds = %entry, %for.body
+  %indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
+  %arrayidx = getelementptr inbounds i64* %y, i64 %indvars.iv
+  %0 = load i64* %arrayidx, align 8
+  %call = tail call i64 @llvm.ctlz.i64(i64 %0, i1 true) nounwind readnone
+  %arrayidx4 = getelementptr inbounds i64* %x, i64 %indvars.iv
+  store i64 %call, i64* %arrayidx4, align 8
+  %indvars.iv.next = add i64 %indvars.iv, 1
+  %lftr.wideiv = trunc i64 %indvars.iv.next to i32
+  %exitcond = icmp eq i32 %lftr.wideiv, %n
+  br i1 %exitcond, label %for.end, label %for.body
+
+for.end:                                          ; preds = %for.body, %entry
+  ret void
+}

diff --git a/test/Transforms/SLPVectorizer/X86/intrinsic.ll b/test/Transforms/SLPVectorizer/X86/intrinsic.ll
index 30c509369730483cfabfc1150627dc9e4ebfbf61..937252f4146bec06b2f1dd586b7c72d72f7639d3 100644 (file)
--- a/test/Transforms/SLPVectorizer/X86/intrinsic.ll
+++ b/test/Transforms/SLPVectorizer/X86/intrinsic.ll
@@ -117,3 +117,270 @@ entry:
 ; CHECK: store <4 x i32>
 ; CHECK: ret
 }
+
+declare i32 @llvm.ctlz.i32(i32,i1) nounwind readnone
+
+define void @vec_ctlz_i32(i32* %a, i32* %b, i32* %c, i1) {
+entry:
+  %i0 = load i32* %a, align 4
+  %i1 = load i32* %b, align 4
+  %add1 = add i32 %i0, %i1
+  %call1 = tail call i32 @llvm.ctlz.i32(i32 %add1,i1 true) nounwind readnone
+
+  %arrayidx2 = getelementptr inbounds i32* %a, i32 1
+  %i2 = load i32* %arrayidx2, align 4
+  %arrayidx3 = getelementptr inbounds i32* %b, i32 1
+  %i3 = load i32* %arrayidx3, align 4
+  %add2 = add i32 %i2, %i3
+  %call2 = tail call i32 @llvm.ctlz.i32(i32 %add2,i1 true) nounwind readnone
+
+  %arrayidx4 = getelementptr inbounds i32* %a, i32 2
+  %i4 = load i32* %arrayidx4, align 4
+  %arrayidx5 = getelementptr inbounds i32* %b, i32 2
+  %i5 = load i32* %arrayidx5, align 4
+  %add3 = add i32 %i4, %i5
+  %call3 = tail call i32 @llvm.ctlz.i32(i32 %add3,i1 true) nounwind readnone
+
+  %arrayidx6 = getelementptr inbounds i32* %a, i32 3
+  %i6 = load i32* %arrayidx6, align 4
+  %arrayidx7 = getelementptr inbounds i32* %b, i32 3
+  %i7 = load i32* %arrayidx7, align 4
+  %add4 = add i32 %i6, %i7
+  %call4 = tail call i32 @llvm.ctlz.i32(i32 %add4,i1 true) nounwind readnone
+
+  store i32 %call1, i32* %c, align 4
+  %arrayidx8 = getelementptr inbounds i32* %c, i32 1
+  store i32 %call2, i32* %arrayidx8, align 4
+  %arrayidx9 = getelementptr inbounds i32* %c, i32 2
+  store i32 %call3, i32* %arrayidx9, align 4
+  %arrayidx10 = getelementptr inbounds i32* %c, i32 3
+  store i32 %call4, i32* %arrayidx10, align 4
+  ret void
+
+; CHECK-LABEL: @vec_ctlz_i32(
+; CHECK: load <4 x i32>
+; CHECK: load <4 x i32>
+; CHECK: call <4 x i32> @llvm.ctlz.v4i32
+; CHECK: store <4 x i32>
+; CHECK: ret
+}
+
+define void @vec_ctlz_i32_neg(i32* %a, i32* %b, i32* %c, i1) {
+entry:
+  %i0 = load i32* %a, align 4
+  %i1 = load i32* %b, align 4
+  %add1 = add i32 %i0, %i1
+  %call1 = tail call i32 @llvm.ctlz.i32(i32 %add1,i1 true) nounwind readnone
+
+  %arrayidx2 = getelementptr inbounds i32* %a, i32 1
+  %i2 = load i32* %arrayidx2, align 4
+  %arrayidx3 = getelementptr inbounds i32* %b, i32 1
+  %i3 = load i32* %arrayidx3, align 4
+  %add2 = add i32 %i2, %i3
+  %call2 = tail call i32 @llvm.ctlz.i32(i32 %add2,i1 false) nounwind readnone
+
+  %arrayidx4 = getelementptr inbounds i32* %a, i32 2
+  %i4 = load i32* %arrayidx4, align 4
+  %arrayidx5 = getelementptr inbounds i32* %b, i32 2
+  %i5 = load i32* %arrayidx5, align 4
+  %add3 = add i32 %i4, %i5
+  %call3 = tail call i32 @llvm.ctlz.i32(i32 %add3,i1 true) nounwind readnone
+
+  %arrayidx6 = getelementptr inbounds i32* %a, i32 3
+  %i6 = load i32* %arrayidx6, align 4
+  %arrayidx7 = getelementptr inbounds i32* %b, i32 3
+  %i7 = load i32* %arrayidx7, align 4
+  %add4 = add i32 %i6, %i7
+  %call4 = tail call i32 @llvm.ctlz.i32(i32 %add4,i1 false) nounwind readnone
+
+  store i32 %call1, i32* %c, align 4
+  %arrayidx8 = getelementptr inbounds i32* %c, i32 1
+  store i32 %call2, i32* %arrayidx8, align 4
+  %arrayidx9 = getelementptr inbounds i32* %c, i32 2
+  store i32 %call3, i32* %arrayidx9, align 4
+  %arrayidx10 = getelementptr inbounds i32* %c, i32 3
+  store i32 %call4, i32* %arrayidx10, align 4
+  ret void
+
+; CHECK-LABEL: @vec_ctlz_i32_neg(
+; CHECK-NOT: call <4 x i32> @llvm.ctlz.v4i32
+
+}
+
+
+declare i32 @llvm.cttz.i32(i32,i1) nounwind readnone
+
+define void @vec_cttz_i32(i32* %a, i32* %b, i32* %c, i1) {
+entry:
+  %i0 = load i32* %a, align 4
+  %i1 = load i32* %b, align 4
+  %add1 = add i32 %i0, %i1
+  %call1 = tail call i32 @llvm.cttz.i32(i32 %add1,i1 true) nounwind readnone
+
+  %arrayidx2 = getelementptr inbounds i32* %a, i32 1
+  %i2 = load i32* %arrayidx2, align 4
+  %arrayidx3 = getelementptr inbounds i32* %b, i32 1
+  %i3 = load i32* %arrayidx3, align 4
+  %add2 = add i32 %i2, %i3
+  %call2 = tail call i32 @llvm.cttz.i32(i32 %add2,i1 true) nounwind readnone
+
+  %arrayidx4 = getelementptr inbounds i32* %a, i32 2
+  %i4 = load i32* %arrayidx4, align 4
+  %arrayidx5 = getelementptr inbounds i32* %b, i32 2
+  %i5 = load i32* %arrayidx5, align 4
+  %add3 = add i32 %i4, %i5
+  %call3 = tail call i32 @llvm.cttz.i32(i32 %add3,i1 true) nounwind readnone
+
+  %arrayidx6 = getelementptr inbounds i32* %a, i32 3
+  %i6 = load i32* %arrayidx6, align 4
+  %arrayidx7 = getelementptr inbounds i32* %b, i32 3
+  %i7 = load i32* %arrayidx7, align 4
+  %add4 = add i32 %i6, %i7
+  %call4 = tail call i32 @llvm.cttz.i32(i32 %add4,i1 true) nounwind readnone
+
+  store i32 %call1, i32* %c, align 4
+  %arrayidx8 = getelementptr inbounds i32* %c, i32 1
+  store i32 %call2, i32* %arrayidx8, align 4
+  %arrayidx9 = getelementptr inbounds i32* %c, i32 2
+  store i32 %call3, i32* %arrayidx9, align 4
+  %arrayidx10 = getelementptr inbounds i32* %c, i32 3
+  store i32 %call4, i32* %arrayidx10, align 4
+  ret void
+
+; CHECK-LABEL: @vec_cttz_i32(
+; CHECK: load <4 x i32>
+; CHECK: load <4 x i32>
+; CHECK: call <4 x i32> @llvm.cttz.v4i32
+; CHECK: store <4 x i32>
+; CHECK: ret
+}
+
+define void @vec_cttz_i32_neg(i32* %a, i32* %b, i32* %c, i1) {
+entry:
+  %i0 = load i32* %a, align 4
+  %i1 = load i32* %b, align 4
+  %add1 = add i32 %i0, %i1
+  %call1 = tail call i32 @llvm.cttz.i32(i32 %add1,i1 true) nounwind readnone
+
+  %arrayidx2 = getelementptr inbounds i32* %a, i32 1
+  %i2 = load i32* %arrayidx2, align 4
+  %arrayidx3 = getelementptr inbounds i32* %b, i32 1
+  %i3 = load i32* %arrayidx3, align 4
+  %add2 = add i32 %i2, %i3
+  %call2 = tail call i32 @llvm.cttz.i32(i32 %add2,i1 false) nounwind readnone
+
+  %arrayidx4 = getelementptr inbounds i32* %a, i32 2
+  %i4 = load i32* %arrayidx4, align 4
+  %arrayidx5 = getelementptr inbounds i32* %b, i32 2
+  %i5 = load i32* %arrayidx5, align 4
+  %add3 = add i32 %i4, %i5
+  %call3 = tail call i32 @llvm.cttz.i32(i32 %add3,i1 true) nounwind readnone
+
+  %arrayidx6 = getelementptr inbounds i32* %a, i32 3
+  %i6 = load i32* %arrayidx6, align 4
+  %arrayidx7 = getelementptr inbounds i32* %b, i32 3
+  %i7 = load i32* %arrayidx7, align 4
+  %add4 = add i32 %i6, %i7
+  %call4 = tail call i32 @llvm.cttz.i32(i32 %add4,i1 false) nounwind readnone
+
+  store i32 %call1, i32* %c, align 4
+  %arrayidx8 = getelementptr inbounds i32* %c, i32 1
+  store i32 %call2, i32* %arrayidx8, align 4
+  %arrayidx9 = getelementptr inbounds i32* %c, i32 2
+  store i32 %call3, i32* %arrayidx9, align 4
+  %arrayidx10 = getelementptr inbounds i32* %c, i32 3
+  store i32 %call4, i32* %arrayidx10, align 4
+  ret void
+
+; CHECK-LABEL: @vec_cttz_i32_neg(
+; CHECK-NOT: call <4 x i32> @llvm.cttz.v4i32
+}
+
+
+declare float @llvm.powi.f32(float, i32)
+define void @vec_powi_f32(float* %a, float* %b, float* %c, i32 %P) {
+entry:
+  %i0 = load float* %a, align 4
+  %i1 = load float* %b, align 4
+  %add1 = fadd float %i0, %i1
+  %call1 = tail call float @llvm.powi.f32(float %add1,i32 %P) nounwind readnone
+
+  %arrayidx2 = getelementptr inbounds float* %a, i32 1
+  %i2 = load float* %arrayidx2, align 4
+  %arrayidx3 = getelementptr inbounds float* %b, i32 1
+  %i3 = load float* %arrayidx3, align 4
+  %add2 = fadd float %i2, %i3
+  %call2 = tail call float @llvm.powi.f32(float %add2,i32 %P) nounwind readnone
+
+  %arrayidx4 = getelementptr inbounds float* %a, i32 2
+  %i4 = load float* %arrayidx4, align 4
+  %arrayidx5 = getelementptr inbounds float* %b, i32 2
+  %i5 = load float* %arrayidx5, align 4
+  %add3 = fadd float %i4, %i5
+  %call3 = tail call float @llvm.powi.f32(float %add3,i32 %P) nounwind readnone
+
+  %arrayidx6 = getelementptr inbounds float* %a, i32 3
+  %i6 = load float* %arrayidx6, align 4
+  %arrayidx7 = getelementptr inbounds float* %b, i32 3
+  %i7 = load float* %arrayidx7, align 4
+  %add4 = fadd float %i6, %i7
+  %call4 = tail call float @llvm.powi.f32(float %add4,i32 %P) nounwind readnone
+
+  store float %call1, float* %c, align 4
+  %arrayidx8 = getelementptr inbounds float* %c, i32 1
+  store float %call2, float* %arrayidx8, align 4
+  %arrayidx9 = getelementptr inbounds float* %c, i32 2
+  store float %call3, float* %arrayidx9, align 4
+  %arrayidx10 = getelementptr inbounds float* %c, i32 3
+  store float %call4, float* %arrayidx10, align 4
+  ret void
+
+; CHECK-LABEL: @vec_powi_f32(
+; CHECK: load <4 x float>
+; CHECK: load <4 x float>
+; CHECK: call <4 x float> @llvm.powi.v4f32
+; CHECK: store <4 x float>
+; CHECK: ret
+}
+
+
+define void @vec_powi_f32_neg(float* %a, float* %b, float* %c, i32 %P, i32 %Q) {
+entry:
+  %i0 = load float* %a, align 4
+  %i1 = load float* %b, align 4
+  %add1 = fadd float %i0, %i1
+  %call1 = tail call float @llvm.powi.f32(float %add1,i32 %P) nounwind readnone
+
+  %arrayidx2 = getelementptr inbounds float* %a, i32 1
+  %i2 = load float* %arrayidx2, align 4
+  %arrayidx3 = getelementptr inbounds float* %b, i32 1
+  %i3 = load float* %arrayidx3, align 4
+  %add2 = fadd float %i2, %i3
+  %call2 = tail call float @llvm.powi.f32(float %add2,i32 %Q) nounwind readnone
+
+  %arrayidx4 = getelementptr inbounds float* %a, i32 2
+  %i4 = load float* %arrayidx4, align 4
+  %arrayidx5 = getelementptr inbounds float* %b, i32 2
+  %i5 = load float* %arrayidx5, align 4
+  %add3 = fadd float %i4, %i5
+  %call3 = tail call float @llvm.powi.f32(float %add3,i32 %P) nounwind readnone
+
+  %arrayidx6 = getelementptr inbounds float* %a, i32 3
+  %i6 = load float* %arrayidx6, align 4
+  %arrayidx7 = getelementptr inbounds float* %b, i32 3
+  %i7 = load float* %arrayidx7, align 4
+  %add4 = fadd float %i6, %i7
+  %call4 = tail call float @llvm.powi.f32(float %add4,i32 %Q) nounwind readnone
+
+  store float %call1, float* %c, align 4
+  %arrayidx8 = getelementptr inbounds float* %c, i32 1
+  store float %call2, float* %arrayidx8, align 4
+  %arrayidx9 = getelementptr inbounds float* %c, i32 2
+  store float %call3, float* %arrayidx9, align 4
+  %arrayidx10 = getelementptr inbounds float* %c, i32 3
+  store float %call4, float* %arrayidx10, align 4
+  ret void
+
+; CHECK-LABEL: @vec_powi_f32_neg(
+; CHECK-NOT: call <4 x float> @llvm.powi.v4f32
+}